Detecting Aspiration During FEES with Narrow Band Imaging in a Clinical Setting

Narrow Band Imaging in Flexible Endoscopic Evaluation of Swallowing-How Does It Work?

PURPOSE

The purposes of this study were to compare the visibility of various color groups in different dilutions using narrow band imaging (NBI) and white light (WL) and to determine an optimal color combination using NBI and WL for multicolor flexible endoscopic evaluation of swallowing (FEES), for example, to test different consistencies.

METHOD

Preliminary examinations were performed in the oral cavity of two healthy volunteers. Various dyes were tested using NBI and WL to evaluate their visibilities. In the case of a clearly discernible color change, the visibility differences in the dilution series under WL and NBI were recorded and compared. Subsequently, an abbreviated dilution series with NBI and WL was performed in a volunteer as part of a swallow endoscopy to determine whether the results from the oral cavity could be transferred to the hypopharynx.

RESULTS

The enhancement of visibility using NBI compared with WL can be proven. When NBI was used, yellow and red food dyes and their mixtures showed distinct color changes. The reacting dyes were still visible under NBI, even at a 10-times-higher dilution, requiring a lower dye concentration for FEES. For increased visibility, the dyes used for FEES with NBI must contain colors from a small range in the yellow and red spectra, which are close to the filter maxima of NBI. Both colors are well visible under WL when combining red and green (secondary color of yellow).

CONCLUSIONS

Certain food colorings are visible 10 times more diluted under NBI than under WL. In a multicolored approach, optimal visibility under NBI and WL can be achieved by combining green and red. This new high-sensitivity FEES should be highlighted to allow an instant distinction from WL-FEES; we suggest "FEES+."

SUPPLEMENTAL MATERIAL

https://doi.org/10.23641/asha.23280290.

AI-Based Detection of Aspiration for Video-Endoscopy with Visual Aids in Meaningful Frames to Interpret the Model Outcome

Disorders of swallowing often lead to pneumonia when material enters the airways (aspiration). Flexible Endoscopic Evaluation of Swallowing (FEES) plays a key role in the diagnostics of aspiration but is prone to human errors. An AI-based tool could facilitate this process. Recent non-endoscopic/non-radiologic attempts to detect aspiration using machine-learning approaches have led to unsatisfying accuracy and show black-box characteristics. Hence, for clinical users it is difficult to trust in these model decisions. Our aim is to introduce an explainable artificial intelligence (XAI) approach to detect aspiration in FEES. Our approach is to teach the AI about the relevant anatomical structures, such as the vocal cords and the glottis, based on 92 annotated FEES videos. Simultaneously, it is trained to detect boluses that pass the glottis and become aspirated. During testing, the AI successfully recognized the glottis and the vocal cords but could not yet achieve satisfying aspiration detection quality. While detection performance must be optimized, our architecture results in a final model that explains its assessment by locating meaningful frames with relevant aspiration events and by highlighting suspected boluses. In contrast to comparable AI tools, our framework is verifiable and interpretable and, therefore, accountable for clinical users.